© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62559
    Prev
    Next
    INDEX
    Explanations

    our cookie and privacy information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HK
    -0.10
    åĿ¤
    -0.09
     Hardcover
    -0.08
    uge
    -0.08
    å§ĵ
    -0.08
    å¼ĢåĪĽ
    -0.08
     HK
    -0.08
    oyal
    -0.08
    WithError
    -0.08
    .ci
    -0.08
    POSITIVE LOGITS
    éļIJç§ģ
    0.13
     privacy
    0.10
    privacy
    0.10
    ités
    0.09
    åįģæĿ¡
    0.09
    ippy
    0.09
     Privacy
    0.09
    ãĥĹãĥ©ãĤ¤
    0.09
    çķİ
    0.09
    خار
    0.09
    Activations Density 0.069%

    No Known Activations